Add ability to use o1-preview and o1-mini as custom models (#17804)

This is a barebones modification of the OpenAI provider code to
accommodate non-streaming completions. This is specifically for the o1
models, which do not support streaming. Tested that this is working by
running a `/workflow` with the following (arbitrarily chosen) settings:

```json
{
  "language_models": {
    "openai": {
      "version": "1",
      "available_models": [
        {
          "name": "o1-preview",
          "display_name": "o1-preview",
          "max_tokens": 128000,
          "max_completion_tokens": 30000
        },
        {
          "name": "o1-mini",
          "display_name": "o1-mini",
          "max_tokens": 128000,
          "max_completion_tokens": 20000
        }
      ]
    }
  },
}
```

Release Notes:

- Changed  `low_speed_timeout_in_seconds` option to `600` for OpenAI
provider to accommodate recent o1 model release.

---------

Co-authored-by: Peter <peter@zed.dev>
Co-authored-by: Bennet <bennet@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>

crates/language_model/src/provider/cloud.rs

@@ -78,6 +78,8 @@ pub struct AvailableModel {
     pub max_tokens: usize,
     /// The maximum number of output tokens allowed by the model.
     pub max_output_tokens: Option<u32>,
+    /// The maximum number of completion tokens allowed by the model (o1-* only)
+    pub max_completion_tokens: Option<u32>,
     /// Override this model with a different Anthropic model for tool calls.
     pub tool_override: Option<String>,
     /// Indicates whether this custom model supports caching.
@@ -257,6 +259,7 @@ impl LanguageModelProvider for CloudLanguageModelProvider {
                     display_name: model.display_name.clone(),
                     max_tokens: model.max_tokens,
                     max_output_tokens: model.max_output_tokens,
+                    max_completion_tokens: model.max_completion_tokens,
                 }),
                 AvailableProvider::Google => CloudModel::Google(google_ai::Model::Custom {
                     name: model.name.clone(),

crates/language_model/src/provider/open_ai.rs

@@ -43,6 +43,7 @@ pub struct AvailableModel {
     pub display_name: Option<String>,
     pub max_tokens: usize,
     pub max_output_tokens: Option<u32>,
+    pub max_completion_tokens: Option<u32>,
 }
 
 pub struct OpenAiLanguageModelProvider {
@@ -175,6 +176,7 @@ impl LanguageModelProvider for OpenAiLanguageModelProvider {
                     display_name: model.display_name.clone(),
                     max_tokens: model.max_tokens,
                     max_output_tokens: model.max_output_tokens,
+                    max_completion_tokens: model.max_completion_tokens,
                 },
             );
         }

crates/language_model/src/settings.rs

@@ -178,11 +178,13 @@ impl OpenAiSettingsContent {
                                     display_name,
                                     max_tokens,
                                     max_output_tokens,
+                                    max_completion_tokens,
                                 } => Some(provider::open_ai::AvailableModel {
                                     name,
                                     max_tokens,
                                     max_output_tokens,
                                     display_name,
+                                    max_completion_tokens,
                                 }),
                                 _ => None,
                             })